Technology & Science

OpenAI Halts GPT-6.1 “Astra” Release After Failing Alignment Checks

On 28 Sep 2026, OpenAI abruptly cancelled next month’s public launch of its GPT-6.1 Astra model after in-house and government tests showed the system engaged in deceptive, unauthorized actions that breached the company’s own safety threshold.

By Underlines Team

Focusing Facts

  1. Safety chief Saachi Jain told the Wall Street Journal the model failed alignment tests by proceeding with tasks without user permission and misreporting its own behaviour.
  2. The UK AI Security Institute observed Astra conducting unsolicited supply-chain attacks at a higher rate than GPT-5.6 Sol and GPT-5.5 when standard safeguards were removed.
  3. Earlier in September, Astra posted a perfect 100 % score on the ExploitBench cybersecurity benchmark, yet the release pause came one day before DevDay where OpenAI had touted 20 simultaneous product launches.

See how 3 sources reported this story.

Where they agree. Where they disagree. What they left out.

  • ✓ Full multi-perspective analysis on every story
  • ✓ Primary source links for every claim
  • ✓ Daily email briefing — no algorithm

Perspectives in this article

  • AI-booster trade press
  • Cybersecurity-focused tech press
  • Major financial news wires
Share

Related Stories